The balance between accuracy and latency is important in facial-expression recognition, particularly in real-time applications where facial expressions can change quickly. Feature modulators are an effective approach for boosting efficiency as they amplify expression-relevant information while keeping computational costs low. However, existing modulators face two prevalent challenges: (i) pooling-based approaches flatten the spatial structure and lose positional information essential for facial expressions and (ii) pooling-free approaches frequently require substantial computational resources owing to long convolution chains, multibranch architectures, or high-dimensional gating mechanisms. In this paper, we propose an efficient modulator that emphasizes spatial refinement with minimal overhead. Specifically, the modulator avoids spatial-resolution collapse by generating a spatial gate directly on the full-resolution spatial grid without global pooling. The modulator adopts a single lightweight branch comprising two convolutions: a large-kernel convolution for context aggregation and a standard convolution that outputs a single-channel score map for spatial gating. Experiments on RAF-DB, FER2013, CK+, and AffectNet demonstrate that the proposed model achieves an effective accuracy–latency balance compared with recent models. The code is available athttps://github.com/tkdgur658/DeSpaM_for_FER.

The growing trend of sharing short videos on social media platforms, where users capture and share moments from their daily lives, has led to an increase in research efforts focused on micro-video recommendations. However, conventional methods oversimplify the modeling of skip behavior, categorizing interactions solely as positive or negative based on whether skipping occurs. This study was motivated by the importance of the first few seconds of micro-videos, leading to a refinement of signals into three distinct categories: highly positive, less positive, and negative. Specifically, we classify skip interactions occurring within a short time as negatives, while those occurring after a delay are categorized as less positive. The proposed dual-level graph and hierarchical ranking loss are designed to effectively learn these fine-grained interactions. Our experiments demonstrated that the proposed method outperformed three conventional methods across eight evaluation measures on two public datasets.

With the steady growth of sensing technology and wearable devices, sensor-based human activity recognition has become essential in widespread applications, such as healthcare monitoring and fitness tracking, where accurate and real-time systems are required. To achieve real-time response, recent studies have focused on lightweight neural network models. Specifically, they designed the network architectures by restricting the number of layers shallowly or connections of each layer. However, these approaches suffer from limited accuracy because the classifier only uses the features at the last layer. In this study, we propose a cheap all-layer aggregation network, CALANet, for accuracy improvement while maintaining the efficiency of existing real-time HAR models. Specifically, CALANet allows the classifier to aggregate the features for all layers, resulting in a performance gain. In addition, this work proves that the theoretical computation cost of CALANet is equivalent to that of conventional networks. Evaluated on seven publicly available datasets, CALANet outperformed existing methods, achieving state-of-the-art performance. The source codes of the CALANet are publicly available at https://github.com/jgpark92/CALANet.

The goal of unsupervised feature selection is to identify a feature subset based on the intrinsic characteristics of a given dataset without user-guided information such as class variables. To achieve this, score functions based on information measures can be used to identify essential features. The major research direction of conventional information-theoretic unsupervised feature selection is to minimize the entropy of the final feature subset. Although the opposite way, i.e., maximization of the joint entropy, can also lead to novel insights, studies in this direction are rare. For example, in the field of information retrieval, selected features that maximize the joint entropy of a feature subset can be effective discriminators for reaching the target tuple in the database. Thus, in this work, we first demonstrate how two feature subsets, each obtained by minimizing/maximizing the joint entropy, respectively, are different based on a toy dataset. By comparing these two feature subsets, we show that the maximization of the joint entropy enhances the pattern discrimination power of the feature subset. Then, we derive a score function by remedying joint entropy calculation; high-dimensional joint entropy calculation is circumvented by using the low-order approximation. The experimental results on 30 public datasets indicate that the proposed method yields superior performance in terms of pattern discrimination power-related measures.

The development of data sensing technology has generated a vast amount of high-dimensional data, posing great challenges for machine learning models. Over the past decades, despite demonstrating its effectiveness in data classification, genetic programming (GP) has still encountered three major challenges when dealing with high-dimensional data: 1) solution diversity; 2) multiclass imbalance; and 3) large feature space. In this article, we have developed a problem-specific multiobjective GP framework (PS-MOGP) for handling classification tasks with high-dimensional data. To reduce the large solution space caused by high dimensionality, we incorporate the recursive feature elimination strategy based on mining the archive of evolved GP solutions. A progressive domination Pareto archive evolution strategy (PD-PAES), which optimizes the objectives in a specific order according to their objectives, is proposed to evaluate the GP individuals and maintain a better diversity of solutions. Besides, to address the seriously imbalanced class issue caused by traditional binary decomposition (BD) one versus rest (OVR) for multiclass classification problems, we design a method named BD with a similar positive and negative class size (BD-SPNCS) to generate a set of auxiliary classifiers. Experimental results on benchmark and real-world datasets demonstrate that our proposed PS-MOGP outperforms state-of-the-art traditional and evolutionary classification methods in the context of high-dimensional data classification.

Human activity recognition is an essential task for human-centered intelligent systems such as healthcare and smart vehicles, which can be accomplished by analyzing time-series signals collected from sensors in wearable devices. In these applications, real-time response is vital because prompt action is necessary for urgent events such as an elderly person falling or driving while drowsy. Although recurrent neural networks have been widely used owing to their temporal modeling capabilities, recent studies have focused on convolutional neural networks (CNNs) that are suitable for real-time responses because they incur lower computational costs. However, CNNs with a manual design may fail to achieve optimal accuracy due to varying computational budgets with applications or devices. In this paper, we propose a novel design framework that uses a mathematical approach to derive a CNN architecture suitable for a given computational budget. As a result, we introduce a grouped temporal shift network (GTSNet) with the network architecture to be flexibly modified by predefining the theoretical computation cost. We demonstrate the effectiveness of our framework in experiments, achieving the best performance for well-known public benchmark datasets under limited computational budgets. The source codes of the GTSNet are publicly available at https://github.com/jgpark92/GTSNet.

Summary Owing to their autonomous nature, computer‐aided pronunciation training systems are regarded as a useful tool for pronunciation training for beginner‐level students, particularly those who feel uncomfortable having their pronunciation corrected in front of other students or who have difficulty with face‐to‐face training for other reasons. In this study, we propose a computer‐assisted pronunciation training system targeting unacceptable pronunciation due to confusion among contextual allophones, a problem that often emerges from phoneme‐based feedback provided during pronunciation training. To consider the different pronunciation of phonemes according to position, the proposed system is implemented to recommend a set of words focusing on phoneme pairs. Experimental results show that the proposed system results in the improvement of pronunciation skills through training sessions that use recommended words containing phoneme pairs that were initially pronounced incorrectly.